Back to Details

torchdrug

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

TorchDrug

TorchDrug

Overview

概述

TorchDrug is a comprehensive PyTorch-based machine learning toolbox for drug discovery and molecular science. Apply graph neural networks, pre-trained models, and task definitions to molecules, proteins, and biological knowledge graphs, including molecular property prediction, protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis planning, with 40+ curated datasets and 20+ model architectures.
TorchDrug是一个基于PyTorch的综合性机器学习工具包，用于药物发现和分子科学研究。可将图神经网络、预训练模型和任务定义应用于分子、蛋白质和生物医学知识图谱，涵盖分子属性预测、蛋白质建模、知识图谱推理、分子生成、逆合成规划等场景，内置40+精选数据集和20+模型架构。

When to Use This Skill

何时使用TorchDrug

This skill should be used when working with:
Data Types:
  • SMILES strings or molecular structures
  • Protein sequences or 3D structures (PDB files)
  • Chemical reactions and retrosynthesis
  • Biomedical knowledge graphs
  • Drug discovery datasets
Tasks:
  • Predicting molecular properties (solubility, toxicity, activity)
  • Protein function or structure prediction
  • Drug-target binding prediction
  • Generating new molecular structures
  • Planning chemical synthesis routes
  • Link prediction in biomedical knowledge bases
  • Training graph neural networks on scientific data
Libraries and Integration:
  • TorchDrug is the primary library
  • Often used with RDKit for cheminformatics
  • Compatible with PyTorch and PyTorch Lightning
  • Integrates with AlphaFold and ESM for proteins
在处理以下场景时可使用TorchDrug：
数据类型：
  • SMILES字符串或分子结构
  • 蛋白质序列或3D结构（PDB文件）
  • 化学反应与逆合成
  • 生物医学知识图谱
  • 药物发现数据集
任务类型：
  • 分子属性预测（溶解度、毒性、活性）
  • 蛋白质功能或结构预测
  • 药物-靶点结合预测
  • 新型分子结构生成
  • 化学合成路线规划
  • 生物医学知识库中的链接预测
  • 在科学数据上训练图神经网络
库与集成：
  • TorchDrug为核心库
  • 常与RDKit联用进行 cheminformatics 研究
  • 兼容PyTorch和PyTorch Lightning
  • 可与AlphaFold和ESM集成处理蛋白质相关任务

Getting Started

快速开始

Installation

安装

bash
uv pip install torchdrug
bash
uv pip install torchdrug

Or with optional dependencies

或安装可选依赖

uv pip install torchdrug[full]
undefined
uv pip install torchdrug[full]
undefined

Quick Example

快速示例

python
from torchdrug import datasets, models, tasks
from torch.utils.data import DataLoader
python
from torchdrug import datasets, models, tasks
from torch.utils.data import DataLoader

Load molecular dataset

加载分子数据集

dataset = datasets.BBBP("~/molecule-datasets/") train_set, valid_set, test_set = dataset.split()
dataset = datasets.BBBP("~/molecule-datasets/") train_set, valid_set, test_set = dataset.split()

Define GNN model

定义GNN模型

model = models.GIN( input_dim=dataset.node_feature_dim, hidden_dims=[256, 256, 256], edge_input_dim=dataset.edge_feature_dim, batch_norm=True, readout="mean" )
model = models.GIN( input_dim=dataset.node_feature_dim, hidden_dims=[256, 256, 256], edge_input_dim=dataset.edge_feature_dim, batch_norm=True, readout="mean" )

Create property prediction task

创建属性预测任务

task = tasks.PropertyPrediction( model, task=dataset.tasks, criterion="bce", metric=["auroc", "auprc"] )
task = tasks.PropertyPrediction( model, task=dataset.tasks, criterion="bce", metric=["auroc", "auprc"] )

Train with PyTorch

使用PyTorch训练

optimizer = torch.optim.Adam(task.parameters(), lr=1e-3) train_loader = DataLoader(train_set, batch_size=32, shuffle=True)
for epoch in range(100): for batch in train_loader: loss = task(batch) optimizer.zero_grad() loss.backward() optimizer.step()
undefined
optimizer = torch.optim.Adam(task.parameters(), lr=1e-3) train_loader = DataLoader(train_set, batch_size=32, shuffle=True)
for epoch in range(100): for batch in train_loader: loss = task(batch) optimizer.zero_grad() loss.backward() optimizer.step()
undefined

Core Capabilities

核心功能

1. Molecular Property Prediction

1. 分子属性预测

Predict chemical, physical, and biological properties of molecules from structure.
Use Cases:
  • Drug-likeness and ADMET properties
  • Toxicity screening
  • Quantum chemistry properties
  • Binding affinity prediction
Key Components:
  • 20+ molecular datasets (BBBP, HIV, Tox21, QM9, etc.)
  • GNN models (GIN, GAT, SchNet)
  • PropertyPrediction and MultipleBinaryClassification tasks
Reference: See 
references/molecular_property_prediction.md
for:
  • Complete dataset catalog
  • Model selection guide
  • Training workflows and best practices
  • Feature engineering details
根据结构预测分子的化学、物理和生物属性。
适用场景：
  • 药物相似性与ADMET属性
  • 毒性筛选
  • 量子化学属性
  • 结合亲和力预测
核心组件：
  • 20+分子数据集（BBBP、HIV、Tox21、QM9等）
  • GNN模型（GIN、GAT、SchNet）
  • PropertyPrediction和MultipleBinaryClassification任务
参考文档： 查看
references/molecular_property_prediction.md
获取：
  • 完整数据集目录
  • 模型选择指南
  • 训练流程与最佳实践
  • 特征工程细节

2. Protein Modeling

2. 蛋白质建模

Work with protein sequences, structures, and properties.
Use Cases:
  • Enzyme function prediction
  • Protein stability and solubility
  • Subcellular localization
  • Protein-protein interactions
  • Structure prediction
Key Components:
  • 15+ protein datasets (EnzymeCommission, GeneOntology, PDBBind, etc.)
  • Sequence models (ESM, ProteinBERT, ProteinLSTM)
  • Structure models (GearNet, SchNet)
  • Multiple task types for different prediction levels
Reference: See 
references/protein_modeling.md
for:
  • Protein-specific datasets
  • Sequence vs structure models
  • Pre-training strategies
  • Integration with AlphaFold and ESM
处理蛋白质序列、结构和属性相关任务。
适用场景：
  • 酶功能预测
  • 蛋白质稳定性与溶解度
  • 亚细胞定位
  • 蛋白质-蛋白质相互作用
  • 结构预测
核心组件：
  • 15+蛋白质数据集（EnzymeCommission、GeneOntology、PDBBind等）
  • 序列模型（ESM、ProteinBERT、ProteinLSTM）
  • 结构模型（GearNet、SchNet）
  • 适用于不同预测层级的多种任务类型
参考文档： 查看
references/protein_modeling.md
获取：
  • 蛋白质专用数据集
  • 序列模型vs结构模型对比
  • 预训练策略
  • 与AlphaFold和ESM的集成方法

3. Knowledge Graph Reasoning

3. 知识图谱推理

Predict missing links and relationships in biological knowledge graphs.
Use Cases:
  • Drug repurposing
  • Disease mechanism discovery
  • Gene-disease associations
  • Multi-hop biomedical reasoning
Key Components:
  • General KGs (FB15k, WN18) and biomedical (Hetionet)
  • Embedding models (TransE, RotatE, ComplEx)
  • KnowledgeGraphCompletion task
Reference: See 
references/knowledge_graphs.md
for:
  • Knowledge graph datasets (including Hetionet with 45k biomedical entities)
  • Embedding model comparison
  • Evaluation metrics and protocols
  • Biomedical applications
预测生物医学知识图谱中缺失的链接和关系。
适用场景：
  • 药物重定位
  • 疾病机制发现
  • 基因-疾病关联
  • 多跳生物医学推理
核心组件：
  • 通用知识图谱（FB15k、WN18）和生物医学知识图谱（Hetionet）
  • 嵌入模型（TransE、RotatE、ComplEx）
  • KnowledgeGraphCompletion任务
参考文档： 查看
references/knowledge_graphs.md
获取：
  • 知识图谱数据集（包含拥有45k生物医学实体的Hetionet）
  • 嵌入模型对比
  • 评估指标与协议
  • 生物医学应用案例

4. Molecular Generation

4. 分子生成

Generate novel molecular structures with desired properties.
Use Cases:
  • De novo drug design
  • Lead optimization
  • Chemical space exploration
  • Property-guided generation
Key Components:
  • Autoregressive generation
  • GCPN (policy-based generation)
  • GraphAutoregressiveFlow
  • Property optimization workflows
Reference: See 
references/molecular_generation.md
for:
  • Generation strategies (unconditional, conditional, scaffold-based)
  • Multi-objective optimization
  • Validation and filtering
  • Integration with property prediction
生成具有目标属性的新型分子结构。
适用场景：
  • 从头药物设计
  • 先导化合物优化
  • 化学空间探索
  • 属性引导的分子生成
核心组件：
  • 自回归生成
  • GCPN（基于策略的生成）
  • GraphAutoregressiveFlow
  • 属性优化流程
参考文档： 查看
references/molecular_generation.md
获取：
  • 生成策略（无条件、条件、基于骨架）
  • 多目标优化
  • 验证与过滤
  • 与属性预测的集成

5. Retrosynthesis

5. 逆合成

Predict synthetic routes from target molecules to starting materials.
Use Cases:
  • Synthesis planning
  • Route optimization
  • Synthetic accessibility assessment
  • Multi-step planning
Key Components:
  • USPTO-50k reaction dataset
  • CenterIdentification (reaction center prediction)
  • SynthonCompletion (reactant prediction)
  • End-to-end Retrosynthesis pipeline
Reference: See 
references/retrosynthesis.md
for:
  • Task decomposition (center ID → synthon completion)
  • Multi-step synthesis planning
  • Commercial availability checking
  • Integration with other retrosynthesis tools
预测从目标分子到起始原料的合成路线。
适用场景：
  • 合成规划
  • 路线优化
  • 合成可及性评估
  • 多步规划
核心组件：
  • USPTO-50k反应数据集
  • CenterIdentification（反应中心预测）
  • SynthonCompletion（反应物预测）
  • 端到端逆合成流水线
参考文档： 查看
references/retrosynthesis.md
获取：
  • 任务分解（中心识别→合成子补全）
  • 多步合成规划
  • 商业可得性检查
  • 与其他逆合成工具的集成

6. Graph Neural Network Models

6. 图神经网络模型

Comprehensive catalog of GNN architectures for different data types and tasks.
Available Models:
  • General GNNs: GCN, GAT, GIN, RGCN, MPNN
  • 3D-aware: SchNet, GearNet
  • Protein-specific: ESM, ProteinBERT, GearNet
  • Knowledge graph: TransE, RotatE, ComplEx, SimplE
  • Generative: GraphAutoregressiveFlow
Reference: See 
references/models_architectures.md
for:
  • Detailed model descriptions
  • Model selection guide by task and dataset
  • Architecture comparisons
  • Implementation tips
适用于不同数据类型和任务的GNN架构全集。
可用模型：
  • 通用GNN：GCN、GAT、GIN、RGCN、MPNN
  • 3D感知模型：SchNet、GearNet
  • 蛋白质专用模型：ESM、ProteinBERT、GearNet
  • 知识图谱模型：TransE、RotatE、ComplEx、SimplE
  • 生成式模型：GraphAutoregressiveFlow
参考文档： 查看
references/models_architectures.md
获取：
  • 详细模型描述
  • 按任务和数据集分类的模型选择指南
  • 架构对比
  • 实现技巧

7. Datasets

7. 数据集

40+ curated datasets spanning chemistry, biology, and knowledge graphs.
Categories:
  • Molecular properties (drug discovery, quantum chemistry)
  • Protein properties (function, structure, interactions)
  • Knowledge graphs (general and biomedical)
  • Retrosynthesis reactions
Reference: See 
references/datasets.md
for:
  • Complete dataset catalog with sizes and tasks
  • Dataset selection guide
  • Loading and preprocessing
  • Splitting strategies (random, scaffold)
40+精选数据集，涵盖化学、生物学和知识图谱领域。
分类：
  • 分子属性（药物发现、量子化学）
  • 蛋白质属性（功能、结构、相互作用）
  • 知识图谱（通用与生物医学）
  • 逆合成反应
参考文档： 查看
references/datasets.md
获取：
  • 完整数据集目录（包含规模和对应任务）
  • 数据集选择指南
  • 加载与预处理方法
  • 拆分策略（随机拆分、骨架拆分）

Common Workflows

常见工作流

Workflow 1: Molecular Property Prediction

工作流1：分子属性预测

Scenario: Predict blood-brain barrier penetration for drug candidates.
Steps:
  1. Load dataset: 
    datasets.BBBP()
  2. Choose model: GIN for molecular graphs
  3. Define task: 
    PropertyPrediction
    with binary classification
  4. Train with scaffold split for realistic evaluation
  5. Evaluate using AUROC and AUPRC
Navigation: 
references/molecular_property_prediction.md
→ Dataset selection → Model selection → Training
场景： 预测候选药物的血脑屏障穿透性。
步骤：
  1. 加载数据集：
    datasets.BBBP()
  2. 选择模型：用于分子图的GIN
  3. 定义任务：用于二分类的
    PropertyPrediction
  4. 使用骨架拆分进行真实场景下的训练
  5. 用AUROC和AUPRC评估模型
导航： 
references/molecular_property_prediction.md
→ 数据集选择 → 模型选择 → 训练

Workflow 2: Protein Function Prediction

工作流2：蛋白质功能预测

Scenario: Predict enzyme function from sequence.
Steps:
  1. Load dataset: 
    datasets.EnzymeCommission()
  2. Choose model: ESM (pre-trained) or GearNet (with structure)
  3. Define task: 
    PropertyPrediction
    with multi-class classification
  4. Fine-tune pre-trained model or train from scratch
  5. Evaluate using accuracy and per-class metrics
Navigation: 
references/protein_modeling.md
→ Model selection (sequence vs structure) → Pre-training strategies
场景： 根据序列预测酶功能。
步骤：
  1. 加载数据集：
    datasets.EnzymeCommission()
  2. 选择模型：ESM（预训练）或GearNet（基于结构）
  3. 定义任务：用于多分类的
    PropertyPrediction
  4. 微调预训练模型或从头训练
  5. 用准确率和各类别指标评估模型
导航： 
references/protein_modeling.md
→ 模型选择（序列vs结构） → 预训练策略

Workflow 3: Drug Repurposing via Knowledge Graphs

工作流3：基于知识图谱的药物重定位

Scenario: Find new disease treatments in Hetionet.
Steps:
  1. Load dataset: 
    datasets.Hetionet()
  2. Choose model: RotatE or ComplEx
  3. Define task: 
    KnowledgeGraphCompletion
  4. Train with negative sampling
  5. Query for "Compound-treats-Disease" predictions
  6. Filter by plausibility and mechanism
Navigation: 
references/knowledge_graphs.md
→ Hetionet dataset → Model selection → Biomedical applications
场景： 在Hetionet中寻找新的疾病治疗方案。
步骤：
  1. 加载数据集：
    datasets.Hetionet()
  2. 选择模型：RotatE或ComplEx
  3. 定义任务：
    KnowledgeGraphCompletion
  4. 用负采样训练模型
  5. 查询“化合物-治疗-疾病”预测结果
  6. 根据合理性和作用机制过滤结果
导航： 
references/knowledge_graphs.md
→ Hetionet数据集 → 模型选择 → 生物医学应用

Workflow 4: De Novo Molecule Generation

工作流4：从头分子生成

Scenario: Generate drug-like molecules optimized for target binding.
Steps:
  1. Train property predictor on activity data
  2. Choose generation approach: GCPN for RL-based optimization
  3. Define reward function combining affinity, drug-likeness, synthesizability
  4. Generate candidates with property constraints
  5. Validate chemistry and filter by drug-likeness
  6. Rank by multi-objective scoring
Navigation: 
references/molecular_generation.md
→ Conditional generation → Multi-objective optimization
场景： 生成针对靶点结合优化的类药分子。
步骤：
  1. 在活性数据上训练属性预测器
  2. 选择生成方法：基于RL优化的GCPN
  3. 定义结合亲和力、类药性、可合成性的奖励函数
  4. 生成带有属性约束的候选分子
  5. 验证化学合理性并按类药性过滤
  6. 按多目标评分排序
导航： 
references/molecular_generation.md
→ 条件生成 → 多目标优化

Workflow 5: Retrosynthesis Planning

工作流5：逆合成规划

Scenario: Plan synthesis route for target molecule.
Steps:
  1. Load dataset: 
    datasets.USPTO50k()
  2. Train center identification model (RGCN)
  3. Train synthon completion model (GIN)
  4. Combine into end-to-end retrosynthesis pipeline
  5. Apply recursively for multi-step planning
  6. Check commercial availability of building blocks
Navigation: 
references/retrosynthesis.md
→ Task types → Multi-step planning
场景： 为目标分子规划合成路线。
步骤：
  1. 加载数据集：
    datasets.USPTO50k()
  2. 训练反应中心识别模型（RGCN）
  3. 训练合成子补全模型（GIN）
  4. 组合为端到端逆合成流水线
  5. 递归应用进行多步规划
  6. 检查构建模块的商业可得性
导航： 
references/retrosynthesis.md
→ 任务类型 → 多步规划

Integration Patterns

集成模式

With RDKit

与RDKit集成

Convert between TorchDrug molecules and RDKit:
python
from torchdrug import data
from rdkit import Chem
在TorchDrug分子与RDKit之间转换：
python
from torchdrug import data
from rdkit import Chem

SMILES → TorchDrug molecule

SMILES → TorchDrug分子

smiles = "CCO" mol = data.Molecule.from_smiles(smiles)
smiles = "CCO" mol = data.Molecule.from_smiles(smiles)

TorchDrug → RDKit

TorchDrug → RDKit

rdkit_mol = mol.to_molecule()
rdkit_mol = mol.to_molecule()

RDKit → TorchDrug

RDKit → TorchDrug

rdkit_mol = Chem.MolFromSmiles(smiles) mol = data.Molecule.from_molecule(rdkit_mol)
undefined
rdkit_mol = Chem.MolFromSmiles(smiles) mol = data.Molecule.from_molecule(rdkit_mol)
undefined

With AlphaFold/ESM

与AlphaFold/ESM集成

Use predicted structures:
python
from torchdrug import data
使用预测结构：
python
from torchdrug import data

Load AlphaFold predicted structure

加载AlphaFold预测结构

protein = data.Protein.from_pdb("AF-P12345-F1-model_v4.pdb")
protein = data.Protein.from_pdb("AF-P12345-F1-model_v4.pdb")

Build graph with spatial edges

构建带空间边的图

graph = protein.residue_graph( node_position="ca", edge_types=["sequential", "radius"], radius_cutoff=10.0 )
undefined
graph = protein.residue_graph( node_position="ca", edge_types=["sequential", "radius"], radius_cutoff=10.0 )
undefined

With PyTorch Lightning

与PyTorch Lightning集成

Wrap tasks for Lightning training:
python
import pytorch_lightning as pl

class LightningTask(pl.LightningModule):
    def __init__(self, torchdrug_task):
        super().__init__()
        self.task = torchdrug_task

    def training_step(self, batch, batch_idx):
        return self.task(batch)

    def validation_step(self, batch, batch_idx):
        pred = self.task.predict(batch)
        target = self.task.target(batch)
        return {"pred": pred, "target": target}

    def configure_optimizers(self):
        return torch.optim.Adam(self.parameters(), lr=1e-3)
将任务包装为Lightning训练模块：
python
import pytorch_lightning as pl

class LightningTask(pl.LightningModule):
    def __init__(self, torchdrug_task):
        super().__init__()
        self.task = torchdrug_task

    def training_step(self, batch, batch_idx):
        return self.task(batch)

    def validation_step(self, batch, batch_idx):
        pred = self.task.predict(batch)
        target = self.task.target(batch)
        return {"pred": pred, "target": target}

    def configure_optimizers(self):
        return torch.optim.Adam(self.parameters(), lr=1e-3)

Technical Details

技术细节

For deep dives into TorchDrug's architecture:
Core Concepts: See 
references/core_concepts.md
for:
  • Architecture philosophy (modular, configurable)
  • Data structures (Graph, Molecule, Protein, PackedGraph)
  • Model interface and forward function signature
  • Task interface (predict, target, forward, evaluate)
  • Training workflows and best practices
  • Loss functions and metrics
  • Common pitfalls and debugging
如需深入了解TorchDrug的架构：
核心概念： 查看
references/core_concepts.md
获取：
  • 架构设计理念（模块化、可配置）
  • 数据结构（Graph、Molecule、Protein、PackedGraph）
  • 模型接口与前向函数签名
  • 任务接口（predict、target、forward、evaluate）
  • 训练流程与最佳实践
  • 损失函数与指标
  • 常见陷阱与调试方法

Quick Reference Cheat Sheet

速查表

Choose Dataset:
  • Molecular property → 
    references/datasets.md
    → Molecular section
  • Protein task → 
    references/datasets.md
    → Protein section
  • Knowledge graph → 
    references/datasets.md
    → Knowledge graph section
Choose Model:
  • Molecules → 
    references/models_architectures.md
    → GNN section → GIN/GAT/SchNet
  • Proteins (sequence) → 
    references/models_architectures.md
    → Protein section → ESM
  • Proteins (structure) → 
    references/models_architectures.md
    → Protein section → GearNet
  • Knowledge graph → 
    references/models_architectures.md
    → KG section → RotatE/ComplEx
Common Tasks:
  • Property prediction → 
    references/molecular_property_prediction.md
    or 
    references/protein_modeling.md
  • Generation → 
    references/molecular_generation.md
  • Retrosynthesis → 
    references/retrosynthesis.md
  • KG reasoning → 
    references/knowledge_graphs.md
Understand Architecture:
  • Data structures → 
    references/core_concepts.md
    → Data Structures
  • Model design → 
    references/core_concepts.md
    → Model Interface
  • Task design → 
    references/core_concepts.md
    → Task Interface
选择数据集：
  • 分子属性任务 → 
    references/datasets.md
    → 分子部分
  • 蛋白质任务 → 
    references/datasets.md
    → 蛋白质部分
  • 知识图谱任务 → 
    references/datasets.md
    → 知识图谱部分
选择模型：
  • 分子任务 → 
    references/models_architectures.md
    → GNN部分 → GIN/GAT/SchNet
  • 蛋白质（序列）任务 → 
    references/models_architectures.md
    → 蛋白质部分 → ESM
  • 蛋白质（结构）任务 → 
    references/models_architectures.md
    → 蛋白质部分 → GearNet
  • 知识图谱任务 → 
    references/models_architectures.md
    → KG部分 → RotatE/ComplEx
常见任务：
  • 属性预测 → 
    references/molecular_property_prediction.md
    或 
    references/protein_modeling.md
  • 分子生成 → 
    references/molecular_generation.md
  • 逆合成 → 
    references/retrosynthesis.md
  • KG推理 → 
    references/knowledge_graphs.md
架构理解：
  • 数据结构 → 
    references/core_concepts.md
    → 数据结构
  • 模型设计 → 
    references/core_concepts.md
    → 模型接口
  • 任务设计 → 
    references/core_concepts.md
    → 任务接口

Troubleshooting Common Issues

常见问题排查

Issue: Dimension mismatch errors → Check 
model.input_dim
matches 
dataset.node_feature_dim
→ See 
references/core_concepts.md
→ Essential Attributes
Issue: Poor performance on molecular tasks → Use scaffold splitting, not random → Try GIN instead of GCN → See 
references/molecular_property_prediction.md
→ Best Practices
Issue: Protein model not learning → Use pre-trained ESM for sequence tasks → Check edge construction for structure models → See 
references/protein_modeling.md
→ Training Workflows
Issue: Memory errors with large graphs → Reduce batch size → Use gradient accumulation → See 
references/core_concepts.md
→ Memory Efficiency
Issue: Generated molecules are invalid → Add validity constraints → Post-process with RDKit validation → See 
references/molecular_generation.md
→ Validation and Filtering
问题：维度不匹配错误 → 检查
model.input_dim
是否与
dataset.node_feature_dim
匹配 → 查看
references/core_concepts.md
→ 核心属性
问题：分子任务性能不佳 → 使用骨架拆分而非随机拆分 → 尝试用GIN替代GCN → 查看
references/molecular_property_prediction.md
→ 最佳实践
问题：蛋白质模型无法收敛 → 针对序列任务使用预训练ESM模型 → 检查结构模型的边构建逻辑 → 查看
references/protein_modeling.md
→ 训练流程
问题：大图导致内存错误 → 减小批量大小 → 使用梯度累积 → 查看
references/core_concepts.md
→ 内存优化
问题：生成的分子无效 → 添加有效性约束 → 用RDKit验证进行后处理 → 查看
references/molecular_generation.md
→ 验证与过滤

Resources

资源

Official Documentation: https://torchdrug.ai/docs/ GitHub: https://github.com/DeepGraphLearning/torchdrug Paper: TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery
官方文档： https://torchdrug.ai/docs/ GitHub： https://github.com/DeepGraphLearning/torchdrug 论文： TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery

Summary

总结

Navigate to the appropriate reference file based on your task:
  1. Molecular property prediction → 
    molecular_property_prediction.md
  2. Protein modeling → 
    protein_modeling.md
  3. Knowledge graphs → 
    knowledge_graphs.md
  4. Molecular generation → 
    molecular_generation.md
  5. Retrosynthesis → 
    retrosynthesis.md
  6. Model selection → 
    models_architectures.md
  7. Dataset selection → 
    datasets.md
  8. Technical details → 
    core_concepts.md
Each reference provides comprehensive coverage of its domain with examples, best practices, and common use cases.
根据你的任务类型导航至对应的参考文档：
  1. 分子属性预测 → 
    molecular_property_prediction.md
  2. 蛋白质建模 → 
    protein_modeling.md
  3. 知识图谱 → 
    knowledge_graphs.md
  4. 分子生成 → 
    molecular_generation.md
  5. 逆合成 → 
    retrosynthesis.md
  6. 模型选择 → 
    models_architectures.md
  7. 数据集选择 → 
    datasets.md
  8. 技术细节 → 
    core_concepts.md
每个参考文档都包含对应领域的全面内容，涵盖示例、最佳实践和常见使用场景。